如何做好
Loop Engineering？

Q1 给出了"Loop ≠ ReAct + 4 机制 + 4 失败 + 5 repo + 量化数据"。Q2 进入下一步：具体怎么做？8 个 best practice 按"影响度 + 实现成本 + 可替代性"3 维加权排序。

§1Ranked Ladder · 8 Best Practice

§23 个必做 + 5 个 nice-to-have

§3代码示例 · ReAct + Stuck Detection

经典 ReAct + 我加的 stuck detection 实战版：

def react_loop_with_safety(question: str, max_iter: int = 10):
    scratchpad = f"Question: {question}\n"
    action_history = []  # 用于 stuck detection
    total_tokens = 0
    TOKEN_BUDGET = 50000

    for i in range(max_iter):
        # Cost / Token limit
        if total_tokens > TOKEN_BUDGET:
            return "❌ Token budget exceeded"

        # 1. Think
        response = llm.invoke(f"{scratchpad}\n\nNext step:")
        thought = response.content
        total_tokens += response.usage.total_tokens

        # 2. Stuck detection (连续 3 次相同 action)
        action = extract_action(thought)
        action_history.append(action)
        if len(action_history) > 3 and action_history[-3:] == [action] * 3:
            # 强制换 path
            thought += "\n\nWait — you've tried this 3 times. Try a different approach."
            response = llm.invoke(f"{scratchpad}\n\n{thought}\n\nNew approach:")

        # 3. Act + Observe
        ...

关键设计：3 层防护 — max_iter (硬上限) + stuck detection (软提示) + token budget (成本上限)。这 3 层是 loop 工程化的核心。

§4代码示例 · Voyager Skill Library

Voyager 论文的核心 — 把每轮成功路径沉淀成 skill：

class SkillLibrary:
    def __init__(self):
        self.skills = {}  # name → {code, description}

    def add_skill(self, name, code, description):
        """Loop 成功后, 把成功路径存为 skill."""
        self.skills[name] = {"code": code, "description": description}

    def get_relevant_skills(self, task: str) -> list:
        """根据任务描述, 找最相关的 skill 列表."""
        # 用 LLM 做 semantic search
        ...
        return relevant_skills

    def execute_skill(self, name):
        return self.skills[name]["code"]

# Loop 中使用
def loop_with_skills(task: str):
    library = SkillLibrary()
    for i in range(100):
        # 1. 找相关 skill
        skills = library.get_relevant_skills(task)

        # 2. 用 skill + think/act
        prompt = f"Available skills: {skills}\nTask: {task}\n\nNext step:"
        response = llm.invoke(prompt)

        # 3. 成功后存 skill
        if "success" in response:
            library.add_skill(f"skill_{i}", response.tool_code, response.description)

核心洞察：loop 越跑越聪明，因为每次成功都沉淀为 skill。这是 Voyager 排 8.05 第一的关键。

§5所以 · Q2 答案

§6下一个问题

Q2 给出了"8 best practice + 3 必做 + 5 nice-to-have + 代码示例"。Q3 进入 项目中应用 — 5 种典型项目 × 4 时间窗 · 何时应用哪个 best practice。